feat(web): resolve Anthropic thinking config from model capabilities

CHANGELOG.md

@@ -11,6 +11,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [EE] Added prompt caching for Ask Sourcebot. For Anthropic models, the static prompt prefix (tool definitions, system prompt, and conversation history) is marked with a cache breakpoint so it is billed at the provider's discounted cache-read rate on subsequent agent steps and follow-up turns. Toggle with `SOURCEBOT_CHAT_PROMPT_CACHING_ENABLED` (default `true`). [#1278](https://github.com/sourcebot-dev/sourcebot/pull/1278)
 - [EE] Added a cached-token breakdown to the Ask Sourcebot message details, showing what share of the input tokens were served from the model provider's prompt cache. [#1278](https://github.com/sourcebot-dev/sourcebot/pull/1278)
 
+### Changed
+- Anthropic thinking mode (adaptive vs. extended) is now resolved from the model's capabilities via the Anthropic Models API instead of a hardcoded model list. [#1294](https://github.com/sourcebot-dev/sourcebot/pull/1294)
+
 ### Fixed
 - Upgraded `protobufjs` to `^7.6.2`. [#1281](https://github.com/sourcebot-dev/sourcebot/pull/1281)
 - Upgraded `picomatch` to `^4.0.4`. [#1283](https://github.com/sourcebot-dev/sourcebot/pull/1283)

packages/web/package.json

@@ -26,6 +26,7 @@
     "@ai-sdk/openai-compatible": "^2.0.41",
     "@ai-sdk/react": "^3.0.169",
     "@ai-sdk/xai": "^3.0.83",
+    "@anthropic-ai/sdk": "^0.104.0",
     "@auth/prisma-adapter": "^2.11.1",
     "@aws-sdk/credential-providers": "^3.1036.0",
     "@bprogress/next": "^3.2.12",

packages/web/src/features/chat/llm.server.ts

@@ -1,6 +1,8 @@
 import 'server-only';
 
 import { createPostHogClient, tryGetPostHogDistinctId } from "@/lib/posthog";
+import { logger } from "./logger";
+import Anthropic from "@anthropic-ai/sdk";
 import { createAmazonBedrock } from '@ai-sdk/amazon-bedrock';
 import { AnthropicProviderOptions, createAnthropic } from '@ai-sdk/anthropic';
 import { createAzure } from '@ai-sdk/azure';
@@ -20,6 +22,7 @@ import { LanguageModel } from '@sourcebot/schemas/v3/languageModel.type';
 import { Token } from "@sourcebot/schemas/v3/shared.type";
 import { env, getTokenFromConfig } from '@sourcebot/shared';
 import { extractReasoningMiddleware, JSONValue, wrapLanguageModel } from "ai";
+import * as Sentry from "@sentry/nextjs";
 
 // @note: This module resolves a configured language model into an AI SDK
 // provider object. It is intentionally FSL (open source) provider plumbing —
@@ -68,34 +71,36 @@ export const getAISDKLanguageModelAndOptions = async (config: LanguageModel): Pr
                 };
             }
             case 'anthropic': {
+                const apiKey = config.token
+                    ? await getTokenFromConfig(config.token)
+                    : env.ANTHROPIC_API_KEY;
+                const authToken = config.authToken
+                    ? await getTokenFromConfig(config.authToken)
+                    : env.ANTHROPIC_AUTH_TOKEN;
+                const headers = config.headers
+                    ? await extractLanguageModelKeyValuePairs(config.headers)
+                    : undefined;
+
                 const anthropic = createAnthropic({
                     baseURL: config.baseUrl,
-                    apiKey: config.token
-                        ? await getTokenFromConfig(config.token)
-                        : env.ANTHROPIC_API_KEY,
-                    authToken: config.authToken
-                        ? await getTokenFromConfig(config.authToken)
-                        : env.ANTHROPIC_AUTH_TOKEN,
-                    headers: config.headers
-                        ? await extractLanguageModelKeyValuePairs(config.headers)
-                        : undefined,
+                    apiKey,
+                    authToken,
+                    headers,
                 });
 
-                const isAdaptiveThinkingSupported =
-                    modelId.startsWith('claude-opus-4-7') ||
-                    modelId.startsWith('claude-opus-4-8');
+                const thinking = await tryResolveAnthropicThinkingConfig({
+                    modelId,
+                    baseUrl: config.baseUrl,
+                    apiKey,
+                    authToken,
+                    headers,
+                });
 
                 return {
                     model: anthropic(modelId),
                     providerOptions: {
                         anthropic: {
-                            thinking: isAdaptiveThinkingSupported ? {
-                                type: "adaptive",
-                                display: "summarized"
-                            } : {
-                                type: "enabled",
-                                budgetTokens: env.ANTHROPIC_THINKING_BUDGET_TOKENS,
-                            }
+                            ...(thinking ? { thinking } : {}),
                         } satisfies AnthropicProviderOptions,
                     },
                 };
@@ -344,3 +349,111 @@ const extractLanguageModelKeyValuePairs = async (
 
     return resolvedPairs;
 };
+
+type AnthropicThinkingConfig = NonNullable<AnthropicProviderOptions['thinking']>;
+const anthropicThinkingConfigCache = new Map<string, AnthropicThinkingConfig | undefined>();
+
+/**
+ * Resolves the `thinking` provider option we pass to the
+ * ai sdk for anthropic models. Queries the Models API to
+ * determine the model's capabilities. Returns undefined
+ * if we are unable to resolve. Results are cached in a
+ * in-memory cache.
+ * 
+ * @see https://docs.anthropic.com/en/api/models
+ */
+const tryResolveAnthropicThinkingConfig = async ({
+    modelId,
+    baseUrl,
+    apiKey,
+    authToken,
+    headers,
+}: {
+    modelId: string,
+    baseUrl?: string,
+    apiKey?: string,
+    authToken?: string,
+    headers?: Record<string, string>,
+}): Promise<AnthropicThinkingConfig | undefined> => {
+    const cacheKey = `${baseUrl ?? 'default'}::${modelId}`;
+    if (anthropicThinkingConfigCache.has(cacheKey)) {
+        return anthropicThinkingConfigCache.get(cacheKey);
+    }
+
+    const {
+        thinkingConfig,
+        shouldCache
+    } = await (async (): Promise<{ thinkingConfig: AnthropicThinkingConfig | undefined, shouldCache: boolean }> => {
+        try {
+            // `@ai-sdk/anthropic` expects `baseURL` to include the `/v1` path segment,
+            // whereas the SDK client appends `/v1` itself — so strip a trailing `/v1`
+            // from the same configured value before handing it to the client.
+            const baseURL = baseUrl
+                ? (baseUrl.replace(/\/+$/, '').replace(/\/v1$/, '') || undefined)
+                : undefined;
+
+            const client = new Anthropic({
+                apiKey,
+                authToken,
+                baseURL,
+                defaultHeaders: headers,
+                maxRetries: 1,
+            });
+
+            const { capabilities } = await client.models.retrieve(modelId, undefined, {
+                timeout: 10_000,
+            });
+
+            if (!capabilities) {
+                throw new Error('the models API did not return a capabilities object.');
+            }
+
+            const thinking = capabilities.thinking;
+            if (thinking.supported === false) {
+                return {
+                    thinkingConfig: undefined,
+                    shouldCache: true
+                };
+            }
+
+            if (thinking.types.adaptive.supported) {
+                return {
+                    thinkingConfig: {
+                        type: "adaptive",
+                        display: "summarized",
+                    } satisfies AnthropicThinkingConfig,
+                    shouldCache: true,
+                };
+            }
+
+            if (thinking.types.enabled.supported) {
+                return {
+                    thinkingConfig: {
+                        type: "enabled",
+                        budgetTokens: env.ANTHROPIC_THINKING_BUDGET_TOKENS,
+                    } satisfies AnthropicThinkingConfig,
+                    shouldCache: true,
+                };
+            }
+
+            return {
+                thinkingConfig: undefined,
+                shouldCache: true
+            };
+        } catch (error) {
+            Sentry.captureException(error);
+            logger.warn(`Failed to fetch Anthropic model capabilities for '${modelId}'. Omitting the thinking option. ${error}`);
+            return {
+                thinkingConfig: undefined,
+                shouldCache: false
+            };
+        }
+    })();
+
+
+    if (shouldCache) {
+        anthropicThinkingConfigCache.set(cacheKey, thinkingConfig);
+    }
+
+    return thinkingConfig;
+};

yarn.lock

@@ -251,6 +251,23 @@ __metadata:
   languageName: node
   linkType: hard
 
+"@anthropic-ai/sdk@npm:^0.104.0":
+  version: 0.104.0
+  resolution: "@anthropic-ai/sdk@npm:0.104.0"
+  dependencies:
+    json-schema-to-ts: "npm:^3.1.1"
+    standardwebhooks: "npm:^1.0.0"
+  peerDependencies:
+    zod: ^3.25.0 || ^4.0.0
+  peerDependenciesMeta:
+    zod:
+      optional: true
+  bin:
+    anthropic-ai-sdk: bin/cli
+  checksum: 10c0/d73197e0fccea3a8a957a895d4fc637bd95ea2ef5a812dce5e48056b06cb044f837bafdbb0c6a4b154e149b352807b5ef43df05f51ffe6f27832a440e1b07569
+  languageName: node
+  linkType: hard
+
 "@anthropic-ai/sdk@npm:^0.78.0":
   version: 0.78.0
   resolution: "@anthropic-ai/sdk@npm:0.78.0"
@@ -9381,6 +9398,7 @@ __metadata:
     "@ai-sdk/openai-compatible": "npm:^2.0.41"
     "@ai-sdk/react": "npm:^3.0.169"
     "@ai-sdk/xai": "npm:^3.0.83"
+    "@anthropic-ai/sdk": "npm:^0.104.0"
     "@asteasolutions/zod-to-openapi": "npm:7.3.4"
     "@auth/prisma-adapter": "npm:^2.11.1"
     "@aws-sdk/credential-providers": "npm:^3.1036.0"
@@ -9604,6 +9622,13 @@ __metadata:
   languageName: node
   linkType: hard
 
+"@stablelib/base64@npm:^1.0.0":
+  version: 1.0.1
+  resolution: "@stablelib/base64@npm:1.0.1"
+  checksum: 10c0/6330720f021819d19cecfe274111b79a256caa81df478d6b0ae7effc8842b96915b6aeed85926ff05b4d48ec1fc78ad043d928b730ee4e6cc6e8cba6aa097bed
+  languageName: node
+  linkType: hard
+
 "@standard-schema/spec@npm:1.1.0, @standard-schema/spec@npm:^1.1.0":
   version: 1.1.0
   resolution: "@standard-schema/spec@npm:1.1.0"
@@ -14389,6 +14414,13 @@ __metadata:
   languageName: node
   linkType: hard
 
+"fast-sha256@npm:^1.3.0":
+  version: 1.3.0
+  resolution: "fast-sha256@npm:1.3.0"
+  checksum: 10c0/87f9e4baa7639576cf60a2b6235c9f436e1a1c52323abbd8a705b5bea8355500acf176f2aed0c14f2ecd6d6007e26151461bab2f27b8953bcca8d9d6b76a86e4
+  languageName: node
+  linkType: hard
+
 "fast-string-truncated-width@npm:^3.0.2":
   version: 3.0.3
   resolution: "fast-string-truncated-width@npm:3.0.3"
@@ -21492,6 +21524,16 @@ __metadata:
   languageName: node
   linkType: hard
 
+"standardwebhooks@npm:^1.0.0":
+  version: 1.0.0
+  resolution: "standardwebhooks@npm:1.0.0"
+  dependencies:
+    "@stablelib/base64": "npm:^1.0.0"
+    fast-sha256: "npm:^1.3.0"
+  checksum: 10c0/aee097d0f3c05172c19b80df1ed9596a2ce92f8956957650d0bbe47c2ca6d36515796b51d523333cb4a48c889b2ab130d789e7879e14975c4381bc7a61274327
+  languageName: node
+  linkType: hard
+
 "statuses@npm:2.0.1, statuses@npm:^2.0.1":
   version: 2.0.1
   resolution: "statuses@npm:2.0.1"